© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 21289
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to executions, especially in the context of government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    7
    +0.15
    0.7%
    755
    +0.11
    0.5%
    728
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.15
    0.02
    728
    +0.11
    0.01
    755
    +0.11
    0.01
    Negative Logits
    ijn
    -0.74
     Lanka
    -0.73
     Lank
    -0.70
    este
    -0.69
     Tire
    -0.68
     Soda
    -0.68
    IGH
    -0.63
     Thing
    -0.60
     Dew
    -0.60
    aspberry
    -0.59
    POSITIVE LOGITS
    eering
    0.89
     execute
    0.86
    ution
    0.83
     executes
    0.82
    eers
    0.82
    sequence
    0.80
     executed
    0.80
     execution
    0.79
    icts
    0.78
    eer
    0.77
    Activations Density 0.033%

    No Known Activations